One-command Linux server security gateway: auth gateway + attack dashboard + vulnerability scanner + AI assistant. 一条命令部署的 Linux 服务器安全网关：认证网关 + 攻击看板 + 漏洞扫描 + AI 助手

Runtime trust layer for MCP tools. Detects post-approval drift including behavioral effective-permission drift (denied→allowed) that manifest diffing misses and quarantines before execution, and emits tamper-evident Security Receipts.

CLI tool for policy lookups in Symantec Advanced Security Gateway

Zero-trust ICS/OT security gateway featuring Stuxnet-proof AI-policy enforcement, sensor spoofing detection, and automatic network isolation.

Local-first AI WAF, compliance gate, and cryptographic provenance engine for agentic workflows. Intercepts payloads, slashes token spend via Prose-Tax minimization, and mints tamper-evident audit chains on local silicon.

Research-grade Zero-Trust IoT security gateway with mTLS, device identity, behavioral monitoring, AI anomaly detection, and forensic logging.

Korean-first AI security gateway for privacy filtering, policy enforcement, approvals, and audit evidence.

Open-source MCP security gateway for federal and defense AI deployments. Native NIST 800-53 Rev 5.2, NIST AI 600-1, OWASP LLM 2025, and MITRE ATLAS mappings. Dual-mode: transparent in dev, strict in federal. FedRAMP 20x / OSCAL ready.

The Security Kernel for AI Agents — MCP/A2A gateway with policy enforcement, taint tracking, sandboxed execution, deterministic envelopes, and Sigstore audit. OWASP ASI 2026 compliant.

Vektrun Security Gateway - HMAC-sealed COMMS_Hub pipeline with prompt-injection defense + malware scan + Brain Admission Control

A security proxy for the Model Context Protocol. Every tool call gets integrity-checked, policy-checked, inspected, and audited before it runs.